As wind is the basis of all wind energy projects, a precise knowledge about its availability is needed. For ananalysis of the site-specific wind conditions, Virtual Meteorological Masts (VMMs) are frequently used. VMM...As wind is the basis of all wind energy projects, a precise knowledge about its availability is needed. For ananalysis of the site-specific wind conditions, Virtual Meteorological Masts (VMMs) are frequently used. VMMsmake use of site calibrated numerical data to provide precise wind estimates during all phases of a wind energyproject. Typically, numerical data are used for the long-term correlation that is required for estimating theyield of new wind farm projects. However, VMMs can also be used to fill data gaps or during the operationalphase as an additional reference data set to detect degrading sensors. The value of a VMM directly dependson its ability and precision to reproduce site-specific environmental conditions. Commonly, linear regressionis used as state of the art to correct reference data to the site-specific conditions. In this study, a frameworkof 10 different machine-learning methods is tested to investigated the benefit of more advanced methods ontwo offshore and one onshore site. We find significantly improving correlations between the VMMs and the reference data when using more advanced methods and present the most promising ones. The K-NearestNeighbors and AdaBoost regressors show the best results in our study, but Multi-Output Mixture of GaussianProcesses is also very promising. The use of more advanced regression models lead to decreased uncertainties;hence those methods should find its way into industrial applications. The recommended regression models canserve as a starting point for the development of end-user applications and services.展开更多
基金ts Digitale Windboje(FKZ 03EE3024)and“ADWENTURE”(FKZ 03EE2030)funded by the German Federal Ministry for Economic Affairs and Climate Action(BMWK)Other parts were funded by the BMBF project“MADESI”(FKZ 01IS18043B)+2 种基金by the Competence Center for AI and Labour(“kompAKI”,FKZ 02L19C150)The project also benefited from the Hessian Ministry of Higher Education,Research,Science and the Arts(HMWK)project“The Third Wave of AI”.The WRF simulations were performed on the HPC Cluster EDDY,located at the University of Oldenburg(Germany)and were funded by BMWK(FKZ 0324005)We would like to thank the Federal Maritime and Hydrographic Agency(BSH)for providing the met mast data of FINO2 and FINO3,and Engie SA for the SCADA data of R80736.Also we would like to acknowledge ECMWF for providing ERA5 data.
文摘As wind is the basis of all wind energy projects, a precise knowledge about its availability is needed. For ananalysis of the site-specific wind conditions, Virtual Meteorological Masts (VMMs) are frequently used. VMMsmake use of site calibrated numerical data to provide precise wind estimates during all phases of a wind energyproject. Typically, numerical data are used for the long-term correlation that is required for estimating theyield of new wind farm projects. However, VMMs can also be used to fill data gaps or during the operationalphase as an additional reference data set to detect degrading sensors. The value of a VMM directly dependson its ability and precision to reproduce site-specific environmental conditions. Commonly, linear regressionis used as state of the art to correct reference data to the site-specific conditions. In this study, a frameworkof 10 different machine-learning methods is tested to investigated the benefit of more advanced methods ontwo offshore and one onshore site. We find significantly improving correlations between the VMMs and the reference data when using more advanced methods and present the most promising ones. The K-NearestNeighbors and AdaBoost regressors show the best results in our study, but Multi-Output Mixture of GaussianProcesses is also very promising. The use of more advanced regression models lead to decreased uncertainties;hence those methods should find its way into industrial applications. The recommended regression models canserve as a starting point for the development of end-user applications and services.